APS-VLA: Action-Guided and Future-Aware Token Pruning for Efficient Vision-Language-Action Models
Vision-language-action (VLA) policies have demonstrated strong generalization in robotic manipulation, yet processing dense visual tokens often incurs high inference latency. Visual token pruning offers a practical way to reduce this cost, but identifying a compact set of tokens that preserves reliable action generation remains challenging. Existing methods largely rely on static or immediate heuristic cues to estimate token importance. We introduce APS-VLA, a framework that learns visual token selection from robot demonstrations while keeping the pretrained VLA backbone frozen. A lightweight Decision Influence Estimator scores tokens conditioned on current visual observations, language instructions, and robot proprioception. Its training combines two complementary signals: action supervision matches both the full-input policy predictions and demonstrated actions, while an auxiliary visual transition objective uses demonstrated actions to predict subsequent visual features from the selected representation. At deployment, the estimator performs a single hard selection and packing step before the policy's native action-generation procedure; the auxiliary predictor is removed.…
Token pruning for efficient vision-language-action models in robotics
- arXiv
- 2611.13030
- Authors
- Xiaoyang Xing, Chun-Mei Feng, Anthony Cohn, Xiaoliang Gong, Asoke Nandi
- Categories
- cs.AI